Engineering management system based on 5G, BIM and big data

Through an engineering management system based on 5G, BIM and big data, the problem of insufficient analysis of different stages and project in the construction process is solved, more efficient abnormal prediction and risk warning are achieved, and the precision of the analysis results is improved.

CN119026909APending Publication Date: 2024-11-26ANHUI DINGXIN PROJECT MANAGEMENT LTD BY SHARE LTD

Patent Information

Application Number
CN202411122945.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-15
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

It is difficult for the existing technology to independently analyze different stages and different construction projects during the construction process, resulting in insufficient analysis results and low risk estimate efficiency.

Method used

Adopt an engineering management system based on 5G, BIM and big data, and obtain video surveillance data and project logs through the data acquisition module. The BIM model construction module establishes a building model. The data processing module extracts and analyzes the construction data of the room model, and generates anomaly coefficient matrix. The abnormal alarm module provides early warnings to improve the precision of the analysis results.

Benefits of technology

It improves the precision of the analysis results, enhances the efficiency of room abnormality prediction, and allows more accurate observation and analysis of abnormal situations in each room at each construction stage.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119026909A_ABST
    Figure CN119026909A_ABST
Patent Text Reader

Abstract

The invention discloses a project management system based on 5G, BIM and big data, relates to the technical field of project management, and solves the problems that in the prior art, different stages and different construction projects in the construction process are difficult to independently analyze, so that the analysis result is not fine enough; and the risk estimation efficiency is low. The data acquisition module is used for acquiring a plurality of video monitoring data and project logs of each construction site; the BIM model building module is used for building a BIM building model according to the basic engineering data; dividing each room model through clustering analysis to obtain a plurality of storage data groups; the data processing module is used for extracting a completed construction stage corresponding to each room model in the project log and stage construction data corresponding to the completed construction stage; generating a stage abnormal coefficient according to the stage construction data and the stage pre-estimation construction data corresponding to each room model, and generating an early warning signal according to the stage abnormal coefficient; and the room abnormity pre-estimation efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application belongs to the field of engineering management technology and relates to engineering management technology, specifically an engineering management system based on 5G, BIM and big data. Background Art

[0002] BIM (Building Information Modeling) technology belongs to the building information model integration technology. BIM engineering information includes the information generated by all parties in the construction process, that is, the information generated by the project. The above information can be the building model information for collaborative operation during the entire life cycle of the building, or it can be ancillary information related to the building. According to the trend of diversification of BIM model information, BIM engineering information has been derived from traditional three-dimensional information, such as construction information, to construction progress simulation, cost analysis, and even full life cycle operation and maintenance of the building.

[0003] The prior art (invention patent application publication number CN117236894A) discloses a BIM-based engineering monitoring management method and system, including the following steps: based on BIM original data, using data extraction algorithm, extracting the geometry, structure and material information of the project from the BIM model, and generating preliminary engineering feature data. In the present invention, by extracting BIM model data, it is ensured that construction management decisions are based on accurate real-time data, improving decision accuracy, automatic anomaly detection reduces processing delay losses, greedy algorithms and dynamic programming cope with unexpected variables, improve project management flexibility, ant colony optimization algorithm optimizes resource utilization, reduces waste and cost, sliding window technology and residual network monitor costs in real time, reduce over-budget risks, intelligent risk assessment model predicts and evaluates potential risks, and reduces engineering risks. These innovative methods ensure more efficient, accurate and cost-controlled engineering management and monitoring.

[0004] The above-mentioned engineering management system determines whether relevant risks arise during the construction process by uniformly analyzing the real-time data of the entire project. The uniform analysis of real-time data makes it difficult to independently analyze different stages and different construction projects during the construction process, resulting in insufficient precision in the analysis results. As a result, the direction of the analysis and estimation is not clear enough, resulting in low efficiency in risk estimation. Therefore, an engineering management system based on 5G, BIM and big data is needed. Summary of the invention

[0005] The present application aims to solve at least one of the technical problems existing in the prior art; to this end, the present application proposes an engineering management system based on 5G, BIM and big data, which is used to solve the technical problems that the prior art is difficult to independently analyze different stages and different construction projects in the construction process, resulting in insufficient precision in the analysis results; and the efficiency of risk estimation is low.

[0006] To achieve the above-mentioned purpose, the first aspect of the present application provides an engineering management system based on 5G, BIM and big data, including: a data acquisition module, a BIM model building module, a data processing module, a 5G transmission module, an abnormal alarm module and a data storage module;

[0007] The data acquisition module is used to obtain video surveillance data and project logs of various construction sites;

[0008] The BIM model building module: obtains basic engineering data through a data storage module connected thereto, and establishes a BIM building model according to the basic engineering data; obtains basic data of each room model in the BIM building model, and divides each room model into several storage data groups through cluster analysis; and numbers each room model in each storage data group;

[0009] The data processing module: extracts the completed construction stage and the corresponding stage construction data corresponding to each room model in the project log; generates a stage abnormality coefficient according to the corresponding stage construction data and the stage estimated construction data of each room model, generates an abnormality coefficient matrix according to the stage abnormality coefficient, and generates an early warning signal according to the abnormality coefficient matrix;

[0010] The abnormal alarm module is used to obtain an early warning signal and issue an early warning according to the early warning signal;

[0011] The data storage module: establishes a storage sub-library according to the storage data group; and stores corresponding data according to the storage sub-library;

[0012] The 5G transmission module: when receiving the access information, the information to be accessed in the access information is packaged and transmitted via 5G.

[0013] The present application obtains basic engineering data through a data storage module connected thereto, and establishes a BIM building model based on the basic engineering data; obtains basic data of each room model in the BIM building model, and divides each room model into several storage data groups through cluster analysis; performs an abnormality analysis on each room model based on the stage construction data of the completed construction stage corresponding to each room model in each storage data group of the goods and the stage estimated data corresponding to each construction stage; generates an abnormality coefficient corresponding to each room by comprehensively considering the stage construction data of each completed construction stage corresponding to room models of similar types and their corresponding stage estimated data; issues an alarm based on the abnormality coefficient; and improves the sophistication of the analysis results, thereby improving the efficiency of room abnormality estimation.

[0014] Preferably, the method of dividing each room model by cluster analysis to obtain a plurality of storage data groups includes:

[0015] Extracting basic data of each room model in the basic engineering data, wherein the basic data includes the room area of ​​the room model, the estimated total construction cost, and the total material usage corresponding to each building material; preprocessing the basic data;

[0016] Obtaining preprocessed basic data; extracting room area, estimated total cost and total usage of several materials from the basic data; integrating the room area, estimated total cost and total usage of several materials into a feature vector; performing cluster analysis on the feature vectors of each basic data to obtain several clusters, and dividing the basic data corresponding to the feature vectors in the same cluster into a storage data group.

[0017] Preferably, the pretreatment comprises:

[0018] Determine whether there is any missing data in the basic data, wherein the missing data includes missing room area, missing estimated total cost, missing material items, and missing total material usage;

[0019] If yes, the basic data is marked as abnormal data, and a supplementary signal is generated;

[0020] If not, the basic data is marked as normal data;

[0021] Extract the room area, estimated total cost and each material usage in the normal data; normalize the room area in each normal data; normalize the estimated total cost in each normal data; normalize the total usage of each identical material in each normal data;

[0022] The normalized room area, estimated cost and the amount of each material are reintegrated into the pre-processed basic data.

[0023] Preferably, generating each stage abnormality coefficient according to the corresponding stage construction data and stage estimated construction data of each room model includes:

[0024] Extract the actual stage cost and the stage material usage corresponding to each material item from the stage construction data, and mark them as SSij and SZi respectively; extract the estimated stage cost and the estimated stage material usage corresponding to each material item from the stage forecast construction data, and mark them as YSij and YZi respectively; where i is the number of the room model corresponding to the stage construction data in the storage data group; j is the number of the material item corresponding to the material usage of each stage;

[0025] The material deviation coefficient PSij corresponding to each material item is calculated by the formula PSij = (SSij-YSij) / YSij;

[0026] The cost deviation coefficient PZi corresponding to each room model is calculated by the formula PZi = (SZi-YZi) / YZi;

[0027] The stage abnormality coefficient YCi of each completed construction stage corresponding to each room model is calculated by the formula YCi=a×arctan(b×∑(PSij)+c×(PZi×∑(YXik×|PZi-PZk|) / (N-1))); wherein j=1, 2,…, M; M is the total number of material items; k=1, 2,…, N; and k≠i; N is the total number of room models corresponding to the basic data in the storage data group; a, b and c are proportional coefficients; YXik is the influence coefficient of the room model numbered k on the room model numbered i; the stage construction data includes the stage material usage and the stage actual cost; the stage estimated construction data corresponds one-to-one to the stage construction data; and the data types are the same.

[0028] Preferably, the influence coefficient of the room model numbered k on the room model numbered i is obtained in the following manner;

[0029] Obtain feature vector 1 corresponding to the room model numbered i, and obtain feature vector 2 corresponding to the room model numbered k; calculate the Euclidean distance between the feature vector 1 and the feature vector 2 and mark it as OJik;

[0030] The influence coefficient YXik of the room model numbered k on the room model numbered i is calculated by the formula YXik=α×exp(-OJik / BJ); wherein α is the adjustment coefficient, BJ is the average distance; it can be calculated by the formula BJ=∑(OJik) / (N-1); k=1, 2,…, N; and k≠i.

[0031] Preferably, generating the abnormal coefficient matrix according to the stage abnormal coefficients includes:

[0032] Obtain the stage abnormality coefficient YCig of each completed construction stage corresponding to each room model; wherein g is the number of each completed construction stage; use the abnormality coefficient YCig of each stage as the element of the i-th row and g-th column to form a corresponding abnormality coefficient matrix.

[0033] The present application integrates the abnormal coefficients corresponding to each room in the same storage data group at each completed construction stage into an abnormal coefficient matrix in the form of room numbers as rows and stage numbers as columns, so as to facilitate relevant personnel to observe the abnormal conditions of each room at each completed construction stage and conduct corresponding analysis.

[0034] Preferably, generating the warning signal according to the abnormal coefficient matrix includes:

[0035] Obtain an abnormal coefficient matrix; mark the sum of all elements in the abnormal coefficient matrix as a comprehensive abnormal coefficient; mark the sum of all elements in each row of the abnormal coefficient matrix as abnormal coefficient one of the corresponding room model; mark the sum of all elements in each column of the abnormal coefficient matrix as abnormal coefficient two corresponding to the completed construction stage; generate an abnormal warning signal according to the comprehensive abnormal coefficient, abnormal coefficient one and abnormal coefficient two.

[0036] Preferably, generating an abnormal warning signal according to the comprehensive abnormal coefficient, the abnormal coefficient 1 and the abnormal coefficient 2 includes:

[0037] Determine whether the comprehensive abnormality coefficient is greater than the comprehensive abnormality coefficient threshold. If yes, generate an abnormality warning signal; if not, when abnormality coefficient one is greater than abnormality coefficient threshold one, generate a room warning signal corresponding to the room model; when abnormality coefficient two is greater than abnormality coefficient threshold two, generate a stage warning signal corresponding to the completed construction stage; the warning signals include abnormality warning signals, stage warning signals and room warning signals.

[0038] Preferably, said establishing a storage sub-library according to the storage data group comprises:

[0039] A data storage library for each storage data group is established in the data storage module; in each data storage library, a number of room stage sub-libraries and data synthesis sub-libraries corresponding to each element in the abnormal coefficient matrix are established according to the corresponding abnormal coefficient matrix; the room stage sub-library is used to store the video surveillance data and project log of the corresponding room corresponding to the completed construction stage; the data synthesis sub-library is used to store the abnormal coefficient matrix and the corresponding abnormal warning signal generated for each completed construction stage of the corresponding storage data group; the storage sub-library includes a room stage sub-library and a synthesis sub-library.

[0040] Compared with the prior art, the beneficial effects of this application are:

[0041] 1. The present application obtains basic engineering data through a data storage module connected thereto, and establishes a BIM building model based on the basic engineering data; obtains basic data of each room model in the BIM building model, and divides each room model into several storage data groups through cluster analysis; performs an abnormality analysis on each room model based on the stage construction data of the completed construction stage corresponding to each room model in each storage data group of the goods and the stage estimated data corresponding to each construction stage; generates an abnormality coefficient corresponding to each room by comprehensively considering the stage construction data of each completed construction stage corresponding to room models of similar types and their corresponding stage estimated data; issues an alarm based on the abnormality coefficient; improves the sophistication of the analysis results, and thereby improves the efficiency of room abnormality estimation.

[0042] 2. This application integrates the abnormal coefficients corresponding to each room in the same storage data group at each completed construction stage into an abnormal coefficient matrix in the form of room numbers as rows and stage numbers as columns, so as to facilitate relevant personnel to observe the abnormal conditions of each room at each completed construction stage and conduct corresponding analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 This is a schematic diagram of the principle of the engineering management system in this application;

[0045] Figure 2 This is a schematic diagram of the steps in this application;

[0046] Figure 3 A flow chart for generating warning signals in this application. DETAILED DESCRIPTION

[0047] The technical solution of the present application will be described clearly and completely below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0048] See also Figure 1-Figure 2 , the first aspect embodiment of the present application provides an engineering management system based on 5G, BIM and big data, including: a data acquisition module, a BIM model building module, a data processing module, a 5G transmission module, an abnormal alarm module and a data storage module;

[0049] Data acquisition module: obtains several video surveillance data and project logs of each construction site; the surveillance video data is the surveillance data collected by each monitoring device at the construction site; the monitoring device in this embodiment is matched with each room, which can be one-to-one, or one monitoring device can monitor the construction of multiple rooms; the project log is to record various information during construction, including the stage construction data corresponding to each completed construction stage of each room, material consumption data, etc.;

[0050] BIM model building module: obtains basic engineering data through the data storage module connected to it, and establishes a BIM building model based on the basic engineering data; obtains basic data of each room model in the BIM building model, and divides each room model into several storage data groups through cluster analysis; the types of each room model in the data storage group are roughly the same or similar; and each room model in each storage data group is numbered;

[0051] Data processing module: extract the completed construction stage and the corresponding stage construction data corresponding to each room model in the project log; the completed construction stage is the completed construction stage, and the construction stage is set by the relevant staff, such as a construction stage can be one month, one quarter, etc.; the corresponding stage construction data is the material consumption, cost and other data of the corresponding stage; the stage forecast construction data is the planned material consumption, cost and other data of each stage; the stage abnormality coefficient is generated according to the corresponding stage construction data and stage estimated construction data of each room model, and the abnormality coefficient can indicate the difference between the material consumption, cost and other materials of the corresponding completed construction stage time of the corresponding room model and the planned material consumption, cost and other materials; the abnormality coefficient matrix is ​​generated according to the stage abnormality coefficient, and the early warning signal is generated according to the abnormality coefficient matrix;

[0052] Abnormal alarm module: obtains early warning signals and issues early warnings based on the early warning signals;

[0053] Data storage module: establishes a storage sub-library according to the storage data group; and stores corresponding data according to the storage sub-library;

[0054] 5G transmission module: When receiving access information, the information to be accessed in the access information is packaged and transmitted via 5G.

[0055] This embodiment obtains basic engineering data through a data storage module connected to it, and establishes a BIM building model based on the basic engineering data; obtains basic data of each room model in the BIM building model, and divides each room model into several storage data groups through cluster analysis; performs an abnormality analysis on each room model based on the stage construction data of the completed construction stage corresponding to each room model in each storage data group of the goods and the stage estimated data corresponding to each construction stage; generates an abnormality coefficient corresponding to each room by comprehensively considering the stage construction data of each completed construction stage corresponding to room models of similar types and the corresponding stage estimated data; issues an alarm based on the abnormality coefficient; and improves the precision of the analysis results, thereby improving the efficiency of room abnormality estimation.

[0056] Through cluster analysis, each room model is divided into several storage data groups, including:

[0057] Extracting basic data of each room model in the basic engineering data, wherein the basic data includes the room area of ​​the room model, the estimated total construction cost, and the total material usage corresponding to each building material; preprocessing the basic data;

[0058] Obtaining preprocessed basic data; extracting room area, estimated total cost and total usage of several materials from the basic data; integrating the room area, estimated total cost and total usage of several materials into a feature vector; the specific form of the feature vector may be {room area, estimated total cost, total usage of material 1, total usage of material 2, ..., total usage of material n}; performing cluster analysis on the feature vectors of each basic data to obtain several cluster clusters, and dividing the basic data corresponding to the feature vectors in the same cluster cluster into a storage data group.

[0059] This embodiment classifies each room model according to the basic data corresponding to each room model through the cluster analysis method, so that room models with similar basic data can be divided into the same storage data group; this facilitates the subsequent analysis of abnormal conditions in a single room, and allows reference to the construction data of other rooms of the same type; thereby improving the accuracy of the analysis of each room at each construction stage.

[0060] Preprocessing includes: determining whether there is data missing in the basic data, wherein the data missing includes missing room area, missing estimated total cost, missing material items, and missing total material usage;

[0061] If yes, the basic data is marked as abnormal data, and a supplementary signal is generated;

[0062] If not, the basic data is marked as normal data;

[0063] Extract the room area, estimated total cost and each material usage in the normal data; normalize the room area in each normal data; normalize the estimated total cost in each normal data; normalize the total usage of each identical material in each normal data;

[0064] The normalized room area, estimated cost and the amount of each material are reintegrated into the pre-processed basic data.

[0065] Generate abnormal coefficients for each stage according to the corresponding stage construction data and stage estimated construction data of each room model, including:

[0066] Extract the actual stage cost and the stage material usage corresponding to each material item from the stage construction data, and mark them as SSij and SZi respectively; extract the estimated stage cost and the estimated stage material usage corresponding to each material item from the stage forecast construction data, and mark them as YSij and YZi respectively; where i is the number of the room model corresponding to the stage construction data in the storage data group; j is the number of the material item corresponding to the material usage of each stage;

[0067] The material deviation coefficient PSij corresponding to each material item is calculated by the formula PSij = (SSij-YSij) / YSij; in this embodiment, the material deviation coefficient corresponding to each material item is obtained by the above formula. The larger the value of the stage material usage corresponding to the material item minus the corresponding estimated stage material usage, the more the actual usage of the corresponding material item exceeds the planned usage, and the larger the corresponding deviation value; conversely, the smaller it is. When the value of the stage material usage minus the corresponding estimated stage material usage is a negative number, it means that the actual usage of the corresponding material item is less than the planned usage.

[0068] The cost deviation coefficient PZi corresponding to each room model is calculated by the formula PZi=(SZi-YZi) / YZi; in this embodiment, the cost deviation coefficient corresponding to each room model is obtained by the above formula. The larger the value of the actual cost of the stage corresponding to the room model minus the corresponding estimated cost of the stage is, the more the actual consumption of the corresponding room model exceeds the planned consumption, and the larger the corresponding deviation value is; conversely, the smaller it is. When the value of the actual cost of the stage minus the corresponding estimated cost is a negative number, it means that the actual consumption of the corresponding room model is less than the planned consumption.

[0069] The stage abnormality coefficient YCi of each completed construction stage corresponding to each room model is calculated by the formula YCi=a×arctan(b×∑(PSij)+c×(PZi×∑(YXik×|PZi-PZk|) / (N-1))); wherein j=1, 2, ..., M; M is the total number of material items; k=1, 2, ..., N; and k≠i; N is the total number of room models corresponding to the basic data in the storage data group; a, b and c are proportional coefficients, which are set according to experience; YXik is the influence coefficient of the room model numbered k on the room model numbered i; the stage construction data includes the stage material usage and the stage actual cost; the stage estimated construction data corresponds to the stage construction data one by one; and the data types are the same.

[0070] In this embodiment, the above formula is used to calculate the stage abnormality coefficient of each completed construction stage corresponding to each room model; when the material deviation coefficient of the completed construction stage corresponding to the room model is larger, it means that the actual usage of the material items corresponding to each material item exceeds the planned usage; the probability of abnormality is greater, so the abnormality coefficient is set to be larger, otherwise, it is smaller; when the difference between the cost deviation coefficients corresponding to each room model in the same storage data group is larger, it means that the probability of abnormality of the corresponding room is greater; when the cost deviation coefficient of the corresponding room is larger, the corresponding probability of abnormality is greater; therefore, the abnormality coefficient is set to be larger; otherwise, it is smaller.

[0071] The influence coefficient of the room model numbered k on the room model numbered i is obtained by the following method;

[0072] Obtain feature vector 1 corresponding to the room model numbered i, and obtain feature vector 2 corresponding to the room model numbered k; calculate the Euclidean distance between the feature vector 1 and the feature vector 2 and mark it as OJik;

[0073] The influence coefficient YXik of the room model numbered k on the room model numbered i is calculated by the formula YXik = α × exp(-OJik / BJ); wherein α is the adjustment coefficient set according to experience, BJ is the average distance; it can be calculated by the formula BJ = ∑(OJik) / (N-1); k = 1, 2, ..., N; and k≠i; it can also be the average value of the Euclidean distance between each feature vector and the cluster center of its corresponding cluster cluster.

[0074] In this embodiment, the influence coefficient between each room model is set by the Euclidean distance between the feature vectors corresponding to each room model; when the Euclidean distance between the feature vectors corresponding to two room models is smaller, it means that the similarity of the basic data corresponding to the two room models is higher, so the corresponding influence coefficient is set larger; otherwise, it is set smaller.

[0075] Generate an abnormal coefficient matrix according to the stage abnormal coefficient, including:

[0076] Obtain the stage abnormality coefficient YCig of each completed construction stage corresponding to each room model; wherein g is the number of each completed construction stage; use the abnormality coefficient YCig of each stage as the element of the i-th row and g-th column to form a corresponding abnormality coefficient matrix.

[0077] This embodiment integrates the abnormal coefficients corresponding to each room in the same storage data group at each completed construction stage into an abnormal coefficient matrix in the form of room numbers as rows and stage numbers as columns, so as to facilitate relevant personnel to observe the abnormal conditions of each room at each completed construction stage and conduct corresponding analysis.

[0078] See also Figure 3 , generating the warning signal according to the abnormal coefficient matrix, including:

[0079] Obtain an abnormal coefficient matrix; mark the sum of all elements in the abnormal coefficient matrix as a comprehensive abnormal coefficient; mark the sum of all elements in each row of the abnormal coefficient matrix as abnormal coefficient one corresponding to the room model; mark the sum of all elements in each column of the abnormal coefficient matrix as abnormal coefficient two corresponding to the completed construction stage;

[0080] Generate abnormal warning signals based on the comprehensive abnormal coefficient, abnormal coefficient one and abnormal coefficient two, including:

[0081] Determine whether the comprehensive abnormality coefficient is greater than the comprehensive abnormality coefficient threshold. If yes, generate an abnormality warning signal; if not, when abnormality coefficient one is greater than abnormality coefficient threshold one, generate a room warning signal corresponding to the room model; when abnormality coefficient two is greater than abnormality coefficient threshold two, generate a stage warning signal corresponding to the completed construction stage; the warning signal includes an abnormality warning signal, a stage warning signal and a room warning signal; the above-mentioned comprehensive abnormality coefficient threshold, abnormality coefficient one and abnormality coefficient two are all specifically set according to experience.

[0082] This embodiment analyzes the abnormal conditions of all completed construction stages of all current rooms by analyzing the sum of all elements of the entire abnormal coefficient matrix, that is, the sum of all abnormal coefficients in the abnormal coefficient matrix, and generates corresponding alarms; analyzes the abnormal conditions of all completed construction stages according to the sum of abnormal coefficients in different columns of the abnormal coefficient matrix, and generates corresponding alarms; analyzes the abnormal conditions of all completed construction stages of all rooms according to the sum of abnormal coefficients in different rows of the abnormal coefficient matrix, and generates corresponding alarms, making the abnormal analysis results more detailed.

[0083] A storage sub-library is established based on the storage data group, including:

[0084] A data storage library for each storage data group is established in the data storage module; in each data storage library, a number of room stage sub-libraries and data synthesis sub-libraries corresponding to each element in the abnormal coefficient matrix are established according to the corresponding abnormal coefficient matrix; the room stage sub-library is used to store the video surveillance data and project log of the corresponding room corresponding to the completed construction stage; the data synthesis sub-library is used to store the abnormal coefficient matrix generated by each completed construction stage of the corresponding storage data group and the corresponding abnormal warning signal; the storage sub-library includes the room stage sub-library and the synthesis sub-library. It is worth noting that the abnormal coefficient matrix needs to be processed before it is stored, including: each element in the stored abnormal coefficient matrix is ​​associated with its corresponding room stage sub-library access address.

[0085] This embodiment establishes a stage sub-library for each stage in each different room and stores corresponding data, so that subsequent query of the data is more convenient.

[0086] It is worth noting that the data storage module is also used to establish a new room stage sub-library based on the abnormal coefficient matrix, including: obtaining the current coefficient abnormality matrix, when the elements of the current coefficient abnormality matrix and the previous coefficient abnormality matrix increase; then obtaining the increased elements and establishing the corresponding room stage sub-library in the corresponding data storage library; in this embodiment, each room model in each BIM model is associated with the access address of the room stage sub-library corresponding to several stages.

[0087] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0088] How this application works:

[0089] This embodiment obtains basic engineering data through a data storage module connected to it, and establishes a BIM building model based on the basic engineering data; obtains basic data of each room model in the BIM building model, and divides each room model into several storage data groups through cluster analysis; performs an abnormality analysis on each room model based on the stage construction data of the completed construction stage corresponding to each room model in each storage data group of the goods and the stage estimated data corresponding to each construction stage; generates an abnormality coefficient corresponding to each room by comprehensively considering the stage construction data of each completed construction stage corresponding to room models of similar types and the corresponding stage estimated data; issues an alarm based on the abnormality coefficient; and improves the precision of the analysis results, thereby improving the efficiency of room abnormality estimation.

[0090] The above embodiments are only used to illustrate the technical method of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical method of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present application.

Claims

1. An engineering management system based on 5G, BIM and big data, including a data acquisition module, a BIM model building module, a data processing module, an abnormal alarm module and a data storage module; It is characterized in that The data acquisition module is used to obtain video surveillance data and project logs of various construction sites; The BIM model building module: obtains basic engineering data through a data storage module connected thereto, and establishes a BIM building model according to the basic engineering data; obtains basic data of each room model in the BIM building model, and divides each room model into several storage data groups through cluster analysis; and numbers each room model in each storage data group; The data processing module: extracts the completed construction stage and the corresponding stage construction data corresponding to each room model in the project log; generates a stage abnormality coefficient according to the corresponding stage construction data and the stage estimated construction data of each room model, generates an abnormality coefficient matrix according to several stage abnormality coefficients in each stored data group, and generates an early warning signal according to the abnormality coefficient matrix; The abnormal alarm module is used to obtain an early warning signal and issue an early warning according to the early warning signal; The data storage module: establishes a storage sub-library according to the storage data group; And store the corresponding data according to the storage sub-library.

2. According to the engineering management system based on 5G, BIM and big data according to claim 1, It is characterized in that The cluster analysis is used to divide each room model into several storage data groups, including: Extracting basic data of each room model in the basic engineering data, wherein the basic data includes the room area of ​​the room model, the estimated total construction cost, and the total material usage corresponding to each building material; preprocessing the basic data; Obtaining preprocessed basic data; extracting room area, estimated total cost and total usage of several materials from the basic data; integrating the room area, estimated total cost and total usage of several materials into a feature vector; performing cluster analysis on the feature vectors of each basic data to obtain several clusters, and dividing the basic data corresponding to the feature vectors in the same cluster into a storage data group.

3. According to the engineering management system based on 5G, BIM and big data according to claim 2, It is characterized in that The pre-processing comprises: Determine whether there is any missing data in the basic data, wherein the missing data includes missing room area, missing estimated total cost, missing material items, and missing total material usage; If yes, the basic data is marked as abnormal data, and a supplementary signal is generated; If not, the basic data is marked as normal data; Extract the room area, estimated total cost and each material usage in the normal data; normalize the room area in each normal data; normalize the estimated total cost in each normal data; normalize the total usage of each identical material in each normal data; The normalized room area, estimated cost and the amount of each material are reintegrated into the pre-processed basic data.

4. According to the engineering management system based on 5G, BIM and big data according to claim 1, It is characterized in that Generate each stage abnormality coefficient according to the corresponding stage construction data and stage estimated construction data of each room model, including: Extract the actual stage cost and the stage material usage corresponding to each material item from the stage construction data, and mark them as SSij and SZi respectively; extract the estimated stage cost and the estimated stage material usage corresponding to each material item from the stage forecast construction data, and mark them as YSij and YZi respectively; where i is the number of the room model corresponding to the stage construction data in the storage data group; j is the number of the material item corresponding to the material usage of each stage; The material deviation coefficient PSij corresponding to each material item is calculated by the formula PSij = (SSij-YSij) / YSij; The cost deviation coefficient PZi corresponding to each room model is calculated by the formula PZi = (SZi-YZi) / YZi; The stage abnormality coefficient YCi of each completed construction stage corresponding to each room model is calculated by the formula YCi=a×arctan(b×∑(PSij)+c×(PZi×∑(YXik×|PZi-PZk|) / (N-1))); wherein j=1, 2,…, M; M is the total number of material items; k=1, 2,…, N; and k≠i; N is the total number of room models corresponding to the basic data in the storage data group; a, b and c are proportional coefficients; YXik is the influence coefficient of the room model numbered k on the room model numbered i; the stage construction data includes the stage material usage and the stage actual cost; the stage estimated construction data corresponds one-to-one to the stage construction data; and the data types are the same.

5. According to the engineering management system based on 5G, BIM and big data according to claim 4, It is characterized in that The influence coefficient of the room model numbered k on the room model numbered i is obtained in the following manner; Obtain feature vector 1 corresponding to the room model numbered i, and obtain feature vector 2 corresponding to the room model numbered k; calculate the Euclidean distance between the feature vector 1 and the feature vector 2 and mark it as OJik; The influence coefficient YXik of the room model numbered k on the room model numbered i is calculated by the formula YXik=α×exp(-OJik / BJ); wherein α is the adjustment coefficient and BJ is the average distance.

6. According to the engineering management system based on 5G, BIM and big data according to claim 1, It is characterized in that Generating the abnormal coefficient matrix according to the stage abnormal coefficients includes: Obtain the stage abnormality coefficient YCig of each completed construction stage corresponding to each room model; wherein g is the number of each completed construction stage; use the abnormality coefficient YCig of each stage as the element of the i-th row and g-th column to form a corresponding abnormality coefficient matrix.

7. According to the engineering management system based on 5G, BIM and big data according to claim 1, It is characterized in that Generating the warning signal according to the abnormal coefficient matrix includes: Obtain an abnormal coefficient matrix; mark the sum of all elements in the abnormal coefficient matrix as a comprehensive abnormal coefficient; mark the sum of all elements in each row of the abnormal coefficient matrix as abnormal coefficient one of the corresponding room model; mark the sum of all elements in each column of the abnormal coefficient matrix as abnormal coefficient two corresponding to the completed construction stage; generate an abnormal warning signal according to the comprehensive abnormal coefficient, abnormal coefficient one and abnormal coefficient two.

8. According to the engineering management system based on 5G, BIM and big data according to claim 7, It is characterized in that The generating of the abnormal warning signal according to the comprehensive abnormal coefficient, the abnormal coefficient 1 and the abnormal coefficient 2 includes: Determine whether the comprehensive abnormality coefficient is greater than the comprehensive abnormality coefficient threshold. If yes, generate an abnormality warning signal; if not, when abnormality coefficient one is greater than abnormality coefficient threshold one, generate a room warning signal corresponding to the room model; when abnormality coefficient two is greater than abnormality coefficient threshold two, generate a stage warning signal corresponding to the completed construction stage; the warning signals include abnormality warning signals, stage warning signals and room warning signals.

9. According to the engineering management system based on 5G, BIM and big data according to claim 1, It is characterized in that The step of establishing a storage sub-library according to the storage data group includes: A data storage library for each storage data group is established in the data storage module; in each data storage library, a number of room stage sub-libraries and data synthesis sub-libraries corresponding to each element in the abnormal coefficient matrix are established according to the corresponding abnormal coefficient matrix; the room stage sub-library is used to store the video surveillance data and project log of the corresponding room corresponding to the completed construction stage; the data synthesis sub-library is used to store the abnormal coefficient matrix and the corresponding abnormal warning signal generated for each completed construction stage of the corresponding storage data group; the storage sub-library includes a room stage sub-library and a synthesis sub-library.

Citation Information

Patent Citations

  • Engineering monitoring management method and system based on BIM

    CN117236894A

Cited By

  • Building engineering information integration management system and method based on AI model

    CN120494247A